A5026479709- Computational Drug Discovery Methods
- Machine Learning in Materials Science
- Chemical Synthesis and Analysis
- Protein Structure and Dynamics
- Bioinformatics and Genomic Networks
- Biomedical Text Mining and Ontologies
- Semantic Web and Ontologies
- Advanced Text Analysis Techniques
- Fibroblast Growth Factor Research
- Cancer Immunotherapy and Biomarkers
- Ferroptosis and cancer prognosis
- Gene Regulatory Network Analysis
- Cancer, Hypoxia, and Metabolism
- Epigenetics and DNA Methylation
- Gene expression and cancer classification
- Web Data Mining and Analysis
- Microbial Metabolic Engineering and Bioproduction
- Cancer-related gene regulation
- interferon and immune responses
- Microbial Natural Products and Biosynthesis
- Protein Kinase Regulation and GTPase Signaling
- RNA Research and Splicing
- Protein Degradation and Inhibitors
- Cell Image Analysis Techniques
- Metabolomics and Mass Spectrometry Studies
Shanghai Institute of Materia Medica
2023-2024
Chinese Academy of Sciences
2023-2024
University of Chinese Academy of Sciences
2023-2024
State Key Laboratory of Drug Research
2023-2024
Drug Discovery Laboratory (Norway)
2024
Abstract Artificial intelligence transforms drug discovery, with phenotype-based approaches emerging as a promising alternative to target-based methods, overcoming limitations like lack of well-defined targets. While chemical-induced transcriptional profiles offer comprehensive view mechanisms, inherent noise often obscures the true signal, hindering their potential for meaningful insights. Here, we highlight development TranSiGen, deep generative model employing self-supervised...
Extracting knowledge from complex and diverse chemical texts is a pivotal task for both experimental computational chemists. The still considered to be extremely challenging due the complexity of language scientific literature. This study explored power fine-tuned large models (LLMs) on five intricate text mining tasks: compound entity recognition, reaction role labelling, metal-organic framework (MOF) synthesis information extraction, nuclear magnetic resonance spectroscopy (NMR) data...
Abstract Structure-based lead optimization is an open challenge in drug discovery, which still largely driven by hypotheses and depends on the experience of medicinal chemists. Here we propose a pairwise binding comparison network (PBCNet) based physics-informed graph attention mechanism, specifically tailored for ranking relative affinity among congeneric ligands. Benchmarking two held-out sets (provided Schrödinger Merck) containing over 460 ligands 16 targets, PBCNet demonstrated...
Extracting knowledge from complex and diverse chemical texts is a pivotal task for both experimental computational chemists. The still considered to be extremely challenging due the complexity of language scientific literature. This study explored power fine-tuned large models (LLMs) on five intricate text mining tasks: compound entity recognition, reaction role labelling, metal-organic framework (MOF) synthesis information extraction, nuclear magnetic resonance spectroscopy (NMR) data...
Small-molecule fibroblast growth factor receptor (FGFR) inhibitors have emerged as a promising antitumor therapy. Herein, by further optimizing the lead compound 1 under guidance of molecular docking, we obtained series novel covalent FGFR inhibitors. After careful structure–activity relationship analysis, several compounds were identified to exhibit strong inhibitory activity and relatively better physicochemical pharmacokinetic properties compared with those 1. Among them, 2e potently...
Structure-based drug design (SBDD) relies on accurate knowledge of protein structure and ligand-binding conformations. However, most the static conformations obtained by advanced methods such as structural biology de novo folding algorithms often don't meet needs for design. We introduce PackDock, a flexible docking method that combines "conformation selection" "induced fit" mechanisms in two-stage pipeline. The core module this is PackPocket, which uses diffusion model to explore side-chain...
Abstract Background Breast cancer is a serious threat to women’s health with high morbidity and mortality. The development of more effective therapies for the treatment breast strongly warranted. Growing evidence suggests that targeting glucose metabolism may be promising strategy. We previously identified new glyceraldehyde-3-phosphate dehydrogenase (GAPDH) inhibitor, DC-5163, which shows great potential in inhibiting tumor growth. Here, we evaluated anticancer DC-5163 cells. Methods...
Abstract Kinase inhibitors are crucial in cancer treatment, but drug resistance and side effects hinder the development of effective drugs. To address these challenges, it is essential to analyze polypharmacology kinase inhibitor identify compound with high selectivity profile. This study presents KinomeMETA, a framework for profiling activity small molecule across panel 661 kinases. By training meta-learner based on graph neural network fine-tuning create kinase-specific learners,...
Extracting knowledge from complex and diverse chemical texts is a pivotal task for both experimental computational chemists. The still considered to be extremely challenging due the complexity of language scientific literature. This study fine-tuned ChatGPT five intricate text mining tasks: compound entity recognition, reaction role labelling, metal-organic framework (MOF) synthesis information extraction, nuclear magnetic resonance spectroscopy (NMR) data conversion paragraph action...
Structure-based lead optimization is an open challenge in drug discovery, which still largely driven by hypotheses and depends on the experience of medicinal chemists. We here propose a pairwise binding comparison network (PBCNet) based physics-informed graph attention mechanism, specifically tailored for ranking relative affinity among congeneric ligands. Benchmarking two held-out sets (provided Schrödinger, Inc. Merck KGaA) containing over 460 ligands 16 targets, PBCNet demonstrated...
Abstract Three-dimensional (3D) conformations of a small molecule profoundly affect its binding to the target interest, resulting biological effects, and disposition in living organisms, but it is challenging accurately characterize conformational ensemble experimentally. Here, we proposed an autoregressive torsion angle prediction model Tora3D for molecular 3D conformer generation. Rather than directly predicting end-to-end way, predicts set angles rotatable bonds by interpretable method...
Retrosynthetic analysis is a fundamental strategy in the field of organic synthesis, and many computational methods have been developed to address this significant task. A widely adopted approach treat retrosynthetic prediction as sequence-to-sequence (seq2seq) translation task, where Simplified Molecular Input Line Entry System (SMILES) product translated into SMILES its corresponding reactants. However, these sequence-based models using also face issues, including limited performance, lack...
Abstract Enhancing cancer treatment efficacy remains a significant challenge in human health. Immunotherapy has witnessed considerable success recent years as for tumors. However, due to the heterogeneity of diseases, only fraction patients exhibit positive response immune checkpoint inhibitor (ICI) therapy. Various single-gene-based biomarkers and tumor mutational burden (TMB) have been proposed predicting clinical responses ICI; however, their predictive ability is limited. We propose...
<title>Abstract</title> Structure-based drug design (SBDD) relies on accurate knowledge of protein structure and ligand-binding conformations. However, most the static conformations obtained by advanced methods such as structural biology de novo folding algorithms often don’t meet needs for design. We introduce PackDock, a flexible docking method that combines “conformation selection” “induced fit” mechanisms in two-stage pipeline. The core module this is PackPocket, which uses diffusion...
Abstract The emergence of perturbation transcriptomics provides a new perspective and opportunity for drug discovery, but existing analysis methods suffer from inadequate performance limited applicability. In this work, we present PertKGE, method designed to improve compound-protein interaction with knowledge graph embedding transcriptomics. PertKGE incorporates diverse regulatory elements accounts multi-level events within biological systems, leading significant improvements compared...
Abstract MicroRNAs (miRNAs) are critical regulators in various biological processes to cleave or repress translation of messenger RNAs (mRNAs). Accurately predicting miRNA targets is essential for developing miRNA-based therapies diseases such as cancer and cardiovascular disease. Traditional target prediction methods often struggle due incomplete knowledge miRNA-target interactions lack interpretability. To address these limitations, we propose miCGR, an end-to-end deep learning framework...
<title>Abstract</title> Understanding protein structure and dynamics is crucial for basic biology drug design. Conventional methods often provide static conformations that inadequately capture flexibility. We present PackDock, a novel approach combining "conformation selection" "induced fit" mechanisms to model protein-ligand interactions. PackDock's core, PackPocket, uses diffusion sample diverse binding pocket or predict ligand-induced changes. validate PackDock through side-chain packing,...
Kinase inhibitors are crucial in cancer treatment, but drug resistance and side effects hinder the development of effective drugs. To address these challenges, it is essential to analyze polypharmacology kinase inhibitor identify compound with high selectivity profile. This study presents KinomeMETA, a framework for profiling activity small molecule across panel 661 kinases. By training meta-learner based on graph neural network fine-tuning create kinase-specific learners, KinomeMETA...
Abstract Immunotherapy has achieved significant success in tumor treatment. However, due to disease heterogeneity, only a fraction of patients respond well immune checkpoint inhibitor (ICI) To address this issue, we developed Text Graph Convolutional Network (Text GCN) model called TG468 for clinical response prediction, which uses the patient’s whole exome sequencing (WES) data across different cohorts capture molecular profile and heterogeneity tumors. can effectively distinguish survival...
Background: Kinase inhibitors are crucial in cancer treatment, but drug resistance and side effects hinder the development of effective drugs. To address these challenges, it is essential to analyze polypharmacology kinase inhibitor identify compound with high selectivity profile. Methods: This study presents KinomeMETA, a framework for profiling activity small molecule across panel 661 kinases. KinomeMETA implemented by training meta-learner based on graph neural network fine-tuning create...
Abstract With the advancement of high-throughput RNA sequencing technologies, use chemical-induced transcriptional profiling has greatly increased in biomedical research. However, usefulness transcriptomics data is limited by inherent random noise and technical artefacts that may cause systematical biases. These limitations make it challenging to identify true signal perturbation extract knowledge from data. In this study, we propose a deep generative model called Transcriptional Signatures...